10 comments

  • dmayle 44 minutes ago
    Fun... This is something I actually care about...

    I used to keep a version of whisperx around, because I think it's important to have not just transcription, but also timing and speaker identification (e.g. for subtitles)... It depends on pyannote, though, which has some wierd licensing (and is tougher to script the installs because of it), so I wanted to look at something that both had better transcription, and supported diarization (the speaker and timing). I decided on parakeet for the transcription with softformer (the diarization), but most of the available engines for it don't include softformer.

    I coded up an OpenAI compatible server for parakeet-rs ( https://github.com/altunenes/parakeet-rs ) (which does support softformer) and I've been using it with OpenWhispr (a desktop app for transcription that handles all sorts of neat thing).

    I'm doing CPU-only transcription (because I use my GPUs for other stuff and haven't gotten around to adding in the GPU-path), but it's incredibly empowering to be able to have local transcriptions at will.

    • dghlsakjg 27 minutes ago
      This is TTS. Not STT.

      For what you are doing, Senko works really well for diarization along with parakeet.

      Faster and more accurate than Pyannote and whisper on my MacBook anyway.

      • dmayle 14 minutes ago
        You're right... I read the title too quickly... I'll have to look at Senko vs Softformer later...
  • mowmiatlas 10 minutes ago
    Cool I actually got it ported to iPhone’s ANE finally yesterday! So we can get both rt natural local TTS and 4x less battery drainage and thermals
  • dvt 52 minutes ago
    I'm using Kokoro for a fun little side-project browser-based game I'm working on. It's legitimately super good for being only 85mb (for the wasm version) or 300mb (for the webgpu version).
  • teravor 1 hour ago
    kokoro is decent but pocket-tts is much better especially when you rip a good voice. https://github.com/kyutai-labs/pocket-tts

    the onnx version of pocket-tts does perform better. https://huggingface.co/KevinAHM/pocket-tts-onnx

    • mscdex 1 hour ago
      I've found that for CPU inference the PyTorch-based (non-quantized) version of Pocket TTS actually performs (both speed and quality-wise) better than the ONNX version, even after fiddling with all of the knobs that ONNX provides.
      • teravor 1 hour ago
        i found the exact opposite, the pytorch version on the cpu barely does over 2 times realtime while i can get the onnx int8 version to reach 5x.
  • othmanosx 39 minutes ago
    Yeah, we need to keep up with how quickly AI types back to us, typing on the keyboards is no longer quick enough, gotta dictate everything now.
    • croes 4 minutes ago
      Great way to enter your passwords
    • victorbjorklund 35 minutes ago
      This is the opposite way
  • kn100 1 hour ago
    I'm using exactly this TTS engine for my intercom door system I built. The quality of the TTS is very good.
  • elevation 1 hour ago
    Any good debian-ish distros that integrate TTS and STT in a usable shell?
  • 0gs 1 hour ago
    kokoro is surprisingly great at nuance but it's tough to improve that last ~2% or so. kokoro + rvc is really great too; i use that for ELEMENT47, the LLM-centric comedy podcast i do that i wish more people would listen to. (e47.net , feel free to subscribe!)
  • SubiculumCode 57 minutes ago
    kokoro is very nice, but I am disappointed that this wasn't an announcement of a new kokoro version.
  • lostmsu 1 hour ago
    > Apple M2 Pro: 4.5 seconds

    > AMD Ryzen 7 8745HS: 1.5 seconds

    These two can probably do it much faster on their iGPUs.

    • dygd 6 minutes ago
      Yep, and Kokoro-FastAPI (which he already uses) makes it super easy with start-gpu_mac.sh